Automatic segmentation of organs at risk and tumors in CT images of lung cancer from partially labelled datasets with a semi-supervised conditional nnU-Net

Zhang, Guobin; Yang, Zhiyong; Huo, Bin; Chai, Shude; Jiang, Shan

doi:10.1016/j.cmpb.2021.106419

Cited by 19 publications

(8 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The segmentation of radiotherapy targets or OARs based on deep convolutional neural networks has been widely reported, [27][28][29][30][31] among which U-net is one of the most widely used network. Our automatic segmentation accuracy of the bladder using U-net has been able to meet the clinical needs and has been approved by senior clinical physicians.…”

Section: Discussionmentioning

confidence: 99%

Quantitative assessment of adaptive radiotherapy for prostate cancer using deep learning: Bladder dose as a decision criterion

Wan,

Jiang,

Zhu

et al. 2023

Medical Physics

View full text Add to dashboard Cite

BackgroundAdaptive radiotherapy (ART) can incorporate anatomical variations in a reoptimized treatment plan for fractionated radiotherapy. An automatic solution to objectively determine whether ART should be performed immediately after the daily image acquisition is highly desirable.PurposeWe investigate a quantitative criterion for whether ART should be performed in prostate cancer radiotherapy by synthesizing pseudo‐CT (sCT) images and evaluating dosimetric impact on treatment planning using deep learning approaches.Method and materialsPlanning CT (pCT) and daily cone‐beam CT (CBCT) data sets of 74 patients are used to train (60 patients) and evaluate (14 patients) a cycle adversarial generative network (CycleGAN) that performs the task of synthesizing high‐quality sCT from daily CBCT. Automatic delineation (AD) of the bladder is performed on the sCT using the U‐net. The combination of sCT and AD allows us to perform dose calculations based on the up‐to‐date bladder anatomy to determine whether the original treatment plan (ori‐plan) is still applicable. For positive cases that the patients’ anatomical changes and the associated dose calculations warrant re‐planning, we made rapid plan revisions (re‐plan) based on the ori‐plan.ResultsThe mean absolute error within the region‐of‐interests (i.e., body, bladder, fat, muscle) between the sCT and pCT are 41.2, 25.1, 26.5, and 29.0HU, respectively. Taking the calculated results of pCT doses as the standard, for PTV, the gamma passing rates of sCT doses at 1 mm/1%, 2 mm/2% are 87.92%, 98.78%, respectively. The Dice coefficients of the AD‐contours are 0.93 on pCT and 0.91 on sCT. According to the result of dose calculation, we found when the bladder volume underwent a substantial change (79.7%), the bladder dose is still within the safe limit, suggesting it is insufficient to solely use the bladder volume change as a criterion to determine whether adaptive treatment needs to be done. After AD‐contours of the bladder using sCT, there are two cases whose bladder dose . For the two cases, we perform re‐planning to reduce the bladder dose to , under the condition that the PTV meets the prescribed dose.ConclusionWe provide a dose accurate adaptive workflow for prostate cancer patients by using deep learning approaches, and implement ART that adapts to bladder dose. Of note, the specific replanning criterion for whether ART needs to be performed can adapt to different centers’ choices based on their experience and daily observations.

show abstract

Section: Discussionmentioning

confidence: 99%

Quantitative assessment of adaptive radiotherapy for prostate cancer using deep learning: Bladder dose as a decision criterion

Wan,

Jiang,

Zhu

et al. 2023

Medical Physics

View full text Add to dashboard Cite

show abstract

“…A probable reason might be that: U-Net had some inevitable shortcomings, including the inability to extract good features, insufficient high-resolution contour information, and the asymmetry between edge-cutting form and feature image ( Li et al, 2022 ). While nnU-Net realized optimization of preprocessing, training, and data post-processing, which avoided ambiguity in contour segmentation ( Zhang et al, 2021a ). Therefore, the blood-vessel segmenting performance of the nnU-Net model was better than the U-Net model.…”

Section: Discussionmentioning

confidence: 99%

The application of the nnU-Net-based automatic segmentation model in assisting carotid artery stenosis and carotid atherosclerotic plaque evaluation

Zhu

Chen

et al. 2022

Front. Physiol.

View full text Add to dashboard Cite

Objective: No new U-net (nnU-Net) is a newly-developed deep learning neural network, whose advantages in medical image segmentation have been noticed recently. This study aimed to investigate the value of the nnU-Net-based model for computed tomography angiography (CTA) imaging in assisting the evaluation of carotid artery stenosis (CAS) and atherosclerotic plaque.Methods: This study retrospectively enrolled 93 CAS-suspected patients who underwent head and neck CTA examination, then randomly divided them into the training set (N = 70) and the validation set (N = 23) in a 3:1 ratio. The radiologist-marked images in the training set were used for the development of the nnU-Net model, which was subsequently tested in the validation set.Results: In the training set, the nnU-Net had already displayed a good performance for CAS diagnosis and atherosclerotic plaque segmentation. Then, its utility was further confirmed in the validation set: the Dice similarity coefficient value of the nnU-Net model in segmenting background, blood vessels, calcification plaques, and dark spots reached 0.975, 0.974 0.795, and 0.498, accordingly. Besides, the nnU-Net model displayed a good consistency with physicians in assessing CAS (Kappa = 0.893), stenosis degree (Kappa = 0.930), the number of calcification plaque (Kappa = 0.922), non-calcification (Kappa = 0.768) and mixed plaque (Kappa = 0.793), as well as the max thickness of calcification plaque (intraclass correlation coefficient = 0.972). Additionally, the evaluation time of the nnU-Net model was shortened compared with the physicians (27.3 ± 4.4 s vs. 296.8 ± 81.1 s, p < 0.001).Conclusion: The automatic segmentation model based on nnU-Net shows good accuracy, reliability, and efficiency in assisting CTA to evaluate CAS and carotid atherosclerotic plaques.

show abstract

“…12: Illustration of confidence map and its corresponding contour map with σ = 0.25 [117] gans. Zhang et al [122] propose a dual-path semi-supervised conditional nnU-Net that can be trained on a union of partially labelled datasets, segmentation of organs at risk or tumors. Another situation is the integration of different levels of supervision signals.…”

Section: Other Semi-supervised Medical Image Segmentation Methodsmentioning

confidence: 99%

“…However, acquiring such fully annotated training data can still be costly, especially for the tasks of medical image segmentation. To further alleviate the annotation cost, some researches integrate semi-supervised learning with other annotationefficient approaches like utilizing partially labelled datasets [122], leveraging image-level, box-level and pixel-level annotations [123] or scribble supervisions [138], or exploiting noisy labeled data [139].…”

Section: Tionsmentioning

confidence: 99%

Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation

Jiao¹,

Zhang²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Medical image segmentation is a fundamental and critical step in many image-guided clinical approaches. Recent success of deep learning-based segmentation methods usually relies on a large amount of labeled data, which is particularly difficult and costly to obtain especially in the medical imaging domain where only experts can provide reliable and accurate annotations. Semi-supervised learning has emerged as an appealing strategy and been widely applied to medical image segmentation tasks to train deep models with limited annotations. In this paper, we present a comprehensive review of recently proposed semi-supervised learning methods for medical image segmentation and summarized both the technical novelties and empirical results. Furthermore, we analyze and discuss the limitations and several unsolved problems of existing approaches. We hope this review could inspire the research community to explore solutions for this challenge and further promote the developments in medical image segmentation field.

show abstract

Automatic segmentation of organs at risk and tumors in CT images of lung cancer from partially labelled datasets with a semi-supervised conditional nnU-Net

Cited by 19 publications

References 30 publications

Quantitative assessment of adaptive radiotherapy for prostate cancer using deep learning: Bladder dose as a decision criterion

Quantitative assessment of adaptive radiotherapy for prostate cancer using deep learning: Bladder dose as a decision criterion

The application of the nnU-Net-based automatic segmentation model in assisting carotid artery stenosis and carotid atherosclerotic plaque evaluation

Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation

Contact Info

Product

Resources

About